© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-8B
    5. 18-RESID-BATCHTOPK-65K__L0-80
    7. 1156
    Prev
    Next
    INDEX
    Explanations

    numbers following counts or statistics

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    adamkarvonen/qwen3-8b-saes/saes_Qwen_Qwen3-8B_batch_top_k/resid_post_layer_18
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    羯
    -0.26
    å·½
    -0.24
     pragma
    -0.23
    èĿĮ
    -0.23
    å¹´åIJİ
    -0.23
    åIJĮæľŁ
    -0.22
    Ñıн
    -0.21
    严谨
    -0.21
    WithContext
    -0.21
    èıŁ
    -0.21
    POSITIVE LOGITS
    avad
    0.26
    acks
    0.24
     recom
    0.24
     metallic
    0.23
    åĤ¥
    0.23
     sometimes
    0.22
    è´¢çī©
    0.22
    rush
    0.22
     sacrificed
    0.22
     profits
    0.21
    Activations Density 0.004%

    No Known Activations